Geometric Properties of Quasi-Additive Learning Algorithms(Control, Neural Networks and Learning,<Special Section>Nonlinear Theory and its Applications)

スポンサーリンク

概要

• 論文の詳細を見る

• The family of Quasi-Additive (QA) algorithms is a natural generalization of the perceptron learning, which is a kind of on-line learning having two parameter vectors: One is an accumulation of input vectors and the other is a weight vector for prediction associated with the former by a nonlinear function. We show that the vectors have a dually-flat structure from the information-geometric point of view, and this representation makes it easier to discuss the convergence properties.

• 社団法人電子情報通信学会の論文
• 2006-10-01

著者

• Ikeda Kazushi

  Kyoto Univ. Kyoto‐shi Jpn

関連論文

• A Network Analysis of Genetic Algorithms(Biocybernetics, Neurocomputing)
• Geometric Properties of Quasi-Additive Learning Algorithms(Control, Neural Networks and Learning,Nonlinear Theory and its Applications)
• Geometrical Properties of Lifting-Up in the Nu Support Vector Machines(Biocybernetics, Neurocomputing)

スポンサーリンク